AI Engineer – Retrieval

Realweb hiring AI Engineer – Retrieval-Augmented Generation (RAG) in Columbia, MD | LinkedIn Agree & Join LinkedIn By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement, Privacy Policy, and Cookie Policy. AI Engineer – Retrieval-Augmented Generation (RAG) AI Engineer – Retrieval-Augmented Generation (RAG) Realweb Columbia, MD 8 months ago Be among the first 25 applicants See who Realweb has hired for this role No longer accepting applications Direct message the job poster from Realweb Mustafa Hussain AI Strategist | Builder | Global AI Delegate-Ireland Position Overview: The AI Engineer (RAG) is responsible for architecting, developing, and deploying advanced Retrieval-Augmented Generation (RAG) pipelines that power AI-driven document understanding, workflow automation, and enterprise search. This role blends expertise in information retrieval with hands-on production deployment of large language model solutions. Experience: - Design and build scalable RAG pipelines using vector search, hybrid retrieval, reranking, and contextual compression techniques for structured and unstructured data. - Develop and optimize data ingestion, document chunking, and embedding generation workflows; implement and manage vector databases (Milvus, FAISS, Pinecone, pgvector). - Integrate RAG capabilities with LLM systems, APIs, and enterprise applications utilizing frameworks like FastAPI, Flask, and Azure Cognitive Search. - Evaluate and monitor performance using classical IR metrics (recall, precision), LLM-specific metrics (factuality, latency), and real-world application feedback; iterate for continuous improvement. - Ensure production readiness of AI solutions: robust, observable, secure, and aligned with compliance requirements for data privacy and business standards. - Collaborate with cross-functional teams, including product managers, backend engineers, and domain experts, to translate technical capabilities into busines